© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 1-CLT-HP
    7. 9583
    Prev
    Next
    INDEX
    Explanations

    Bank

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ores
    -0.49
    AddHtmlAttribute
    -0.47
     gynhyrchwyd
    -0.45
    :][
    -0.43
    ore
    -0.42
    localctx
    -0.42
    IsContent
    -0.42
     id
    -0.41
     '
    -0.40
     kep
    -0.40
    POSITIVE LOGITS
     itſelf
    0.96
     Majefty
    0.90
    Portail
    0.89
     الحره
    0.87
     purpoſe
    0.86
     houſe
    0.80
     Houſe
    0.77
     myſelf
    0.77
    ſelf
    0.77
     leaſt
    0.75
    Activations Density 0.199%

    No Known Activations